Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tuple
    -0.07
     profile
    -0.07
     #-
    -0.07
    」。
    -0.06
    inning
    -0.06
     beste
    -0.06
     #:
    -0.06
    -from
    -0.06
     DROP
    -0.06
     Metric
    -0.06
    POSITIVE LOGITS
    (egt
    0.07
    řím
    0.06
    كار
    0.06
     ним
    0.06
    τύ
    0.06
    ự
    0.06
     지
    0.06
    	lbl
    0.06
     pož
    0.06
    貸
    0.06
    Act Density 0.039%

    No Known Activations